[PATCH v5 2/4] util/repair: identify and repair "Mixed Up" mangled messages

[Daniel Kahn Gillmor <dkg@fifthhorseman.net>]

This patch implements a functional identification and repair process
for "Mixed Up" MIME messages as described in
https://tools.ietf.org/html/draft-dkg-openpgp-pgpmime-message-mangling-00#section-4.1

The detection test is not entirely complete, in that it does not
verify the contents of the latter two message subparts, but this is
probably safe to skip, because those two parts are unlikely to be
readable anyway, and the only part we are effectively omitting (the
first subpart) is guaranteed to be empty anyway, so its removal can be
reversed if you want to do so.  I've left FIXMEs in the code so that
anyone excited about adding these additional checks can see where to
put them in.

I'll use this functionality in the next two patches.

Signed-off-by: Daniel Kahn Gillmor <dkg@fifthhorseman.net>
---
 util/repair.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++
 util/repair.h | 10 ++++++
 2 files changed, 94 insertions(+)

diff --git a/util/repair.c b/util/repair.c
index 629e6f23..9fba97b7 100644
--- a/util/repair.c
+++ b/util/repair.c
@@ -120,3 +120,87 @@ _notmuch_repair_crypto_payload_skip_legacy_display (GMimeObject *payload)
 	return payload;
     }
 }
+
+/* see
+ * https://tools.ietf.org/html/draft-dkg-openpgp-pgpmime-message-mangling-00#section-4.1.1 */
+static bool
+_notmuch_is_mixed_up_mangled (GMimeObject *part)
+{
+    GMimeMultipart *mpart = NULL;
+    GMimeObject *parts[3] = {NULL, NULL, NULL};
+    GMimeContentType *type = NULL;
+    char *prelude_string = NULL;
+    bool prelude_is_empty;
+
+    if (part == NULL)
+	return false;
+    type = g_mime_object_get_content_type (part);
+    if (type == NULL)
+	return false;
+    if (! g_mime_content_type_is_type (type, "multipart", "mixed"))
+	return false;
+    if (! GMIME_IS_MULTIPART (part)) /* probably impossible */
+	return false;
+    mpart = GMIME_MULTIPART (part);
+    if (mpart == NULL)
+	return false;
+    if (g_mime_multipart_get_count (mpart) != 3)
+	return false;
+    parts[0] = g_mime_multipart_get_part (mpart, 0);
+    if (! g_mime_content_type_is_type (g_mime_object_get_content_type (parts[0]),
+				       "text", "plain"))
+	return false;
+    if (! GMIME_IS_TEXT_PART (parts[0]))
+	return false;
+    parts[1] = g_mime_multipart_get_part (mpart, 1);
+    if (! g_mime_content_type_is_type (g_mime_object_get_content_type (parts[1]),
+				       "application", "pgp-encrypted"))
+	return false;
+    parts[2] = g_mime_multipart_get_part (mpart, 2);
+    if (! g_mime_content_type_is_type (g_mime_object_get_content_type (parts[2]),
+				       "application", "octet-stream"))
+	return false;
+
+    /* Is parts[0] length 0? */
+    prelude_string = g_mime_text_part_get_text (GMIME_TEXT_PART (parts[0]));
+    prelude_is_empty = (prelude_string[0] == '\0');
+    g_free (prelude_string);
+    if (! prelude_is_empty)
+	return false;
+
+    /* FIXME: after decoding and stripping whitespace, is parts[1]
+     * subpart just "Version: 1" ? */
+
+    /* FIXME: can we determine that parts[2] subpart is *only* PGP
+     * encrypted data?  I tried g_mime_part_get_openpgp_data () but
+     * found https://github.com/jstedfast/gmime/issues/60 */
+
+    return true;
+}
+
+
+/* see
+ * https://tools.ietf.org/html/draft-dkg-openpgp-pgpmime-message-mangling-00#section-4.1.2 */
+GMimeObject *
+_notmuch_repair_mixed_up_mangled (GMimeObject *part)
+{
+    GMimeMultipart *mpart = NULL, *mpart_ret = NULL;
+    GMimeObject *ret = NULL;
+
+    if (! _notmuch_is_mixed_up_mangled (part))
+	return NULL;
+    mpart = GMIME_MULTIPART (part);
+    ret = GMIME_OBJECT (g_mime_multipart_encrypted_new ());
+    if (ret == NULL)
+	return NULL;
+    mpart_ret = GMIME_MULTIPART (ret);
+    if (mpart_ret == NULL) {
+	g_object_unref (ret);
+	return NULL;
+    }
+    g_mime_object_set_content_type_parameter (ret, "protocol", "application/pgp-encrypted");
+
+    g_mime_multipart_insert (mpart_ret, 0, g_mime_multipart_get_part (mpart, 1));
+    g_mime_multipart_insert (mpart_ret, 1, g_mime_multipart_get_part (mpart, 2));
+    return ret;
+}
diff --git a/util/repair.h b/util/repair.h
index 9974d693..492f5a20 100644
--- a/util/repair.h
+++ b/util/repair.h
@@ -25,9 +25,19 @@ extern "C" {
  * returned object will only be released when the original part is
  * disposed of.
  */
+
 GMimeObject *
 _notmuch_repair_crypto_payload_skip_legacy_display (GMimeObject *payload);
 
+/* Detecting and repairing "Mixed-Up MIME mangling". see
+ * https://tools.ietf.org/html/draft-dkg-openpgp-pgpmime-message-mangling-00#section-4.1
+ * If this returns NULL, the message was probably not "Mixed up".  If
+ * it returns non-NULL, then there is a newly-allocated MIME part that
+ * represents the repaired version.  The caller is responsible for
+ * ensuring that any returned object is freed with g_object_unref. */
+GMimeObject *
+_notmuch_repair_mixed_up_mangled (GMimeObject *part);
+
 #ifdef __cplusplus
 }
 #endif
-- 
2.23.0